Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Topology segmentation method and device oriented to closed space

A closed space and topological technology, applied in image analysis, image enhancement, instruments, etc., can solve problems such as inability to determine topological space, inability to perform effective segmentation, and high mis-segmentation rate

Active Publication Date: 2018-08-17
BEIJING EVOLVER ROBOTICS TECH CO LTD
View PDF9 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the object of the present invention is to provide a closed space-oriented topological segmentation method and device, to alleviate the high mis-segmentation rate of the existing topological segmentation method, the inability to perform effective segmentation, and the inability to determine the location to which any position in the space belongs. Technical Problems in Topological Spaces

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Topology segmentation method and device oriented to closed space
  • Topology segmentation method and device oriented to closed space
  • Topology segmentation method and device oriented to closed space

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A topological segmentation method for closed spaces, refer to figure 1 , the method includes:

[0036] S102. Obtain target point cloud data of the closed space to be processed, wherein the target point cloud data is preprocessed point cloud data;

[0037] In the embodiment of the present invention, the closed space to be treated includes a family indoor space, and may also include other spaces, which are not specifically limited in the embodiment of the present invention.

[0038] The acquisition of the target point cloud data of the closed space to be processed will be introduced in detail below, and will not be repeated here.

[0039] S104, using density projection and eigenvalue method to extract the point cloud data conforming to the characteristics of the wall in the target point cloud data;

[0040] After obtaining the target point cloud data, the density projection and eigenvalue method are used to extract the point cloud data in the target point cloud data tha...

Embodiment 2

[0155] A topological segmentation device for closed spaces, refer to Figure 8 , the device consists of:

[0156] The acquisition module 11 is configured to acquire target point cloud data of the closed space to be processed, wherein the target point cloud data is preprocessed point cloud data;

[0157] Extraction module 12, for adopting density projection and eigenvalue method to extract the point cloud data that conforms to wall surface feature in target point cloud data;

[0158] The rasterization processing module 13 is used to carry out three-dimensional to two-dimensional projection to the point cloud data conforming to the wall surface characteristics, and rasterizes the projected data to extract a plurality of line segments;

[0159] The first clustering processing module 14 is configured to perform clustering processing on a plurality of line segments by an iterative clustering method to obtain an outline of a closed space to be processed, wherein the outline include...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides a topology segmentation method and device oriented to a closed space, the method comprises: acquiring target point cloud data of a closed space to be processed; and extracting point cloud data, complying with a wall characteristic, from the target point cloud data by a density projection and characteristic value method; performing 3D to 2D projection on the point cloud datacomplying with the wall characteristic, rasterizing the projected data to extract multiple line segments; clustering the multiple line segments by an iterative clustering method to obtain the contourof the closed space to be processed; clustering the grids in the contour by using a point clustering method with multi-directional scanning based on the contour, to obtain a topological segmentation map of the closed space to be processed. The method improves the accuracy of topology segmentation, can effectively segment the closed space, and solves a technical problem that an existing topology segmentation method has high error rate, cannot achieve effective segmentation, and cannot determine the topological space of any location in the space.

Description

technical field [0001] The present invention relates to the technical field of topological segmentation of point cloud space, in particular to a closed space-oriented topological segmentation method and device. Background technique [0002] With the continuous innovation of robot technology, home service robots are flourishing as an important branch of the robot field. Various home service robots emerge in endlessly, with various types and more and more powerful functions, from sweeping robots to companion robots, educational robots, etc. People's requirements for intelligent robots are getting higher and higher. From traditional single functions such as sweeping the floor to today's human-computer interaction, natural language understanding, autonomous navigation, etc., people gradually tend to regard robots as a part of the family. Existence, as a member of the family, for robots with autonomous navigation functions, the cognition of the environment is particularly importa...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06T7/11G06K9/62
CPCG06T7/11G06T2207/10024G06T2207/10028G06T2207/20068G06F18/23
Inventor 廉斌王玉亮
Owner BEIJING EVOLVER ROBOTICS TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com